arXiv subjects

Ziming Wang

Publications and source records attributed to Ziming Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments

We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridging the Sim2Real gap. Powered by Gaussian Splatting and MuJoCo, Discoverse enables massively parallel simulation of multiple sensor modalities and accurate physics, with inclusive supports for existing 3D assets, robot models, and ROS plugins, empowering large-scale robot learning and complex robotic benchmarks. Through extensive experiments on imitation learning, Discoverse demonstrates state-of-the-art zero-shot Sim2Real transfer performance compared to existing simulators. For code and demos: https://air-discoverse.github.io/.

cs.RO↗

arXiv2025

GroupTuner: Efficient Group-Aware Compiler Auto-Tuning

Modern compilers typically provide hundreds of options to optimize program performance, but users often cannot fully leverage them due to the huge number of options. While standard optimization combinations (e.g., -O3) provide reasonable defaults, they often fail to deliver near-peak performance across diverse programs and architectures. To address this challenge, compiler auto-tuning techniques have emerged to automate the discovery of improved option combinations. Existing techniques typically focus on identifying critical options and prioritizing them during the search to improve efficiency. However, due to limited tuning iterations, the resulting data is often sparse and noisy, making it highly challenging to accurately identify critical options. As a result, these algorithms are prone to being trapped in local optima. To address this limitation, we propose GroupTuner, a group-aware auto-tuning technique that directly applies localized mutation to coherent option groups based on historically best-performing combinations, thus avoiding explicitly identifying critical options. By forgoing the need to know precisely which options are most important, GroupTuner maximizes the use of existing performance data, ensuring more targeted exploration. Extensive experiments demonstrate that GroupTuner can efficiently discover competitive option combinations, achieving an average performance improvement of 12.39% over -O3 while requiring only 77.21% of the time compared to the random search algorithm, significantly outperforming state-of-the-art methods.

cs.SE↗

arXiv2025

Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning

Dynamic material handling (DMH) involves the assignment of dynamically arriving material transporting tasks to suitable vehicles in real time for minimising makespan and tardiness. In real-world scenarios, historical task records are usually available, which enables the training of a decision policy on multiple instances consisting of historical records. Recently, reinforcement learning has been applied to solve DMH. Due to the occurrence of dynamic events such as new tasks, adaptability is highly required. Solving DMH is challenging since constraints including task delay should be satisfied. A feedback is received only when all tasks are served, which leads to sparse reward. Besides, making the best use of limited computational resources and historical records for training a robust policy is crucial. The time allocated to different problem instances would highly impact the learning process. To tackle those challenges, this paper proposes a novel adaptive constrained evolutionary reinforcement learning (ACERL) approach, which maintains a population of actors for diverse exploration. ACERL accesses each actor for tackling sparse rewards and constraint violation to restrict the behaviour of the policy. Moreover, ACERL adaptively selects the most beneficial training instances for improving the policy. Extensive experiments on eight training and eight unseen test instances demonstrate the outstanding performance of ACERL compared with several state-of-the-art algorithms. Policies trained by ACERL can schedule the vehicles while fully satisfying the constraints. Additional experiments on 40 unseen noised instances show the robust performance of ACERL. Cross-validation further presents the overall effectiveness of ACREL. Besides, a rigorous ablation study highlights the coordination and benefits of each ingredient of ACERL.

cs.NE↗

arXiv2025

Adaptive Event-triggered Formation Control of Autonomous Vehicles

This paper presents adaptive event-triggered formation control strategies for autonomous vehicles (AVs) subject to longitudinal and lateral motion uncertainties. The proposed framework explores various vehicular formations to enable safe and efficient navigation in complex traffic scenarios, such as narrow passages, collaborative obstacle avoidance, and adaptation to cut-in maneuvers. In contrast to conventional platoon control strategies that rely on predefined communication topologies and continuous state transmission, our approach employs a sampling-based observer to reconstruct vehicle dynamics. Building upon an adaptive backstepping continuous-time controller, we design three distinct event-triggered mechanisms, each offering a different trade-off between formation tracking performance and control efficiency by reducing the frequency of control signal updates. A Lyapunov-based stability analysis is conducted to guarantee bounded tracking errors and to avoid Zeno behavior. Finally, the proposed event-triggered controllers are validated through simulations of vehicular formation in three scenarios, highlighting their impact on traffic safety and mobility.

eess.SY↗

arXiv2025

Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport

In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setting of interest arises when the target label space is a subset of the source label space, leading to the framework of partial domain adaptation (PDA). Typical approaches to PDA involve minimizing a domain alignment term and a weighted empirical loss on the source data, with the aim of transferring knowledge between domains. However, a theoretical basis for this procedure is lacking, and in particular, most existing weighting schemes are heuristic. In this work, we derive generalization bounds for the PDA problem based on partial optimal transport. These bounds corroborate the use of the partial Wasserstein distance as a domain alignment term, and lead to theoretically motivated explicit expressions for the empirical source loss weights. Inspired by these bounds, we devise a practical algorithm for PDA, termed WARMPOT. Through extensive numerical experiments, we show that WARMPOT is competitive with recent approaches, and that our proposed weights improve on existing schemes.

cs.LG↗

arXiv2025

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning

Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fine-tuning a scoring model on the target dataset, which is time-consuming and resource-intensive, or rely on heuristics that fail to fully leverage the model's predictive capabilities. To address these challenges, we propose Data Whisperer, an efficient, training-free, attention-based method that leverages few-shot in-context learning with the model to be fine-tuned. Comprehensive evaluations were conducted on both raw and synthetic datasets across diverse tasks and models. Notably, Data Whisperer achieves superior performance compared to the full GSM8K dataset on the Llama-3-8B-Instruct model, using just 10% of the data, and outperforms existing methods with a 3.1-point improvement and a 7.4$\times$ speedup. The code is available at https://github.com/gszfwsb/Data-Whisperer.

cs.CL↗

arXiv2025

"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models

The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark in Chinese, named ChineseSimpleVQA, aimed at assessing the visual factuality of LVLMs across 8 major topics and 56 subtopics. The key features of this benchmark include a focus on the Chinese language, diverse knowledge types, a multi-hop question construction, high-quality data, static consistency, and easy-to-evaluate through short answers. Moreover, we contribute a rigorous data construction pipeline and decouple the visual factuality into two parts: seeing the world (i.e., object recognition) and discovering knowledge. This decoupling allows us to analyze the capability boundaries and execution mechanisms of LVLMs. Subsequently, we evaluate 34 advanced open-source and closed-source models, revealing critical performance gaps within this field. Our evaluation-friendly code and data have already been open-sourced.

cs.CL↗

arXiv2025

Effective Fixed-Time Control for Constrained Nonlinear System

In this paper, we tackle the state transformation problem in non-strict full state-constrained systems by introducing an adaptive fixed-time control method, utilizing a one-to-one asymmetric nonlinear mapping auxiliary system. Additionally, we develop a class of multi-threshold event-triggered control strategies that facilitate autonomous controller updates, substantially reducing communication resource consumption. Notably, the self-triggered strategy distinguishes itself from other strategies by obviating the need for continuous real-time monitoring of the controller's state variables. By accurately forecasting the subsequent activation instance, this strategy significantly optimizes the efficiency of the control system. Moreover, our theoretical analysis demonstrates that the semi-global practical fixed-time stability (SPFTS) criterion guarantees both tracking accuracy and closed-loop stability under state constraints, with convergence time independent of initial conditions. Finally, simulation results reveal that the proposed method significantly decreases the frequency of control command updates while maintaining tracking accuracy.

eess.SY↗

arXiv2025

Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?

Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs' prior knowledge on calibration during fine-tuning remains understudied. Our research reveals that LLMs' prior knowledge causes potential poor calibration due to the ubiquitous presence of known data in real-world fine-tuning, which appears harmful for calibration. Specifically, data aligned with LLMs' prior knowledge would induce overconfidence, while new knowledge improves calibration. Our findings expose a tension: LLMs' encyclopedic knowledge, while enabling task versatility, undermines calibration through unavoidable knowledge overlaps. To address this, we propose CogCalib, a cognition-aware framework that applies targeted learning strategies according to the model's prior knowledge. Experiments across 7 tasks using 3 LLM families prove that CogCalib significantly improves calibration while maintaining performance, achieving an average 57\% reduction in ECE compared to standard fine-tuning in Llama3-8B. These improvements generalize well to out-of-domain tasks, enhancing the objectivity and reliability of domain-specific LLMs, and making them more trustworthy for critical human-AI interaction applications.

cs.CL↗

arXiv2025

ASRC-SNN: Adaptive Skip Recurrent Connection Spiking Neural Network

In recent years, Recurrent Spiking Neural Networks (RSNNs) have shown promising potential in long-term temporal modeling. Many studies focus on improving neuron models and also integrate recurrent structures, leveraging their synergistic effects to improve the long-term temporal modeling capabilities of Spiking Neural Networks (SNNs). However, these studies often place an excessive emphasis on the role of neurons, overlooking the importance of analyzing neurons and recurrent structures as an integrated framework. In this work, we consider neurons and recurrent structures as an integrated system and conduct a systematic analysis of gradient propagation along the temporal dimension, revealing a challenging gradient vanishing problem. To address this issue, we propose the Skip Recurrent Connection (SRC) as a replacement for the vanilla recurrent structure, effectively mitigating the gradient vanishing problem and enhancing long-term temporal modeling performance. Additionally, we propose the Adaptive Skip Recurrent Connection (ASRC), a method that can learn the skip span of skip recurrent connection in each layer of the network. Experiments show that replacing the vanilla recurrent structure in RSNN with SRC significantly improves the model's performance on temporal benchmark datasets. Moreover, ASRC-SNN outperforms SRC-SNN in terms of temporal modeling capabilities and robustness.

cs.NE↗

arXiv2025

Shared Properties of Merger-driven Long-duration Gamma-Ray Bursts

The recent detections of bright optical/infrared kilonova signals following two long-duration gamma-ray bursts (LGRBs), GRB 211211A and GRB 230307A, have significantly challenged the traditional classification of GRBs. These merger-driven LGRBs may represent a distinct GRB population. Since traditional GRB classification methods often struggle to distinguish merger-driven LGRBs from traditional merger-driven short-duration GRBs resulting from compact object mergers and collapse-driven LGRBs produced by massive stars, this work aims to explore the shared properties in terms of hardness, energy, and duration among currently observed merger-driven LGRB events, thereby identifying their observed differences from the traditional GRB population. We collect a sample of merger-driven LGRBs with known redshifts, including observed information on their main emission (ME) and whole emission (WE) phases. Treating ME and WE properties as two independent sets of information, we apply several GRB classification methodologies to explore their potential shared properties. Using the phenomenologically defined Energy-Hardness (EH) parameter, we identify a probable universal linear correlation across merger-driven LGRBs, regardless of whether their ME or WE phases are considered. We propose that such shared properties of merger-driven LGRBs are unlikely to arise from the low-redshift selection effect and they become particularly intriguing when compared with the relatively weak correlations or lack of correlation observed in traditional merger-driven short-duration GRBs (with or without extended emissions) and collapse-driven LGRBs. Our newly proposed correlation highlights the necessity for further investigation into the observations of merger-driven LGRBs and the physical mechanisms underlying the empirical correlation.

astro-ph.HE↗

arXiv2025

Fixed-Relative-Switched Threshold Strategies for Consensus Tracking Control of Nonlinear Multiagent Systems

This paper investigates event-triggered consensus tracking in nonlinear semi-strict-feedback multi-agent systems involving one leader and multiple followers. We first employ radial basis function neural networks and backstepping techniques to approximate the unknown nonlinear dynamics, facilitating the design of dual observers to measure the unknown states and disturbances. Then three adaptive event-triggered control schemes are proposed: fixed-threshold, relative-threshold, and switched-threshold configurations, each featuring specialized controller architectures and triggering mechanisms. Through Lyapunov stability analysis, we establish that the follower agents can asymptotically track the reference trajectory of the leader, meanwhile all error signals remain uniform bounded. Our proposed control strategies effectively prevent Zeno behaviors through stringent exclusion criteria. Finally, an illustrative example is presented, demonstrating the competitive performance of our control framework in achieving consensus tracking and optimizing triggering efficiency.

eess.SY↗

arXiv2025

Reanalyzing the ringdown signal of GW150914 using the F-statistic method

The ringdown phase of a gravitational wave (GW) signal from a binary black hole merger provides valuable insights into the properties of the final black hole and serves as a critical test of general relativity in the strong-field regime. A key aspect of this investigation is to determine whether the first overtone mode exists in real GW data, as its presence would offer significant implications for our understanding of general relativity under extreme conditions. To address this, we conducted a reanalysis of the ringdown signal from GW150914, using the newly proposed F-statistic method to search for the first overtone mode. Our results are consistent with those obtained through classical time-domain Bayesian inference, indicating that there is no evidence of the first overtone mode in the ringdown signal of GW150914. However, our results show the potentiality of utilizing the F-statistic methodology to unearth nuanced features within GW signals, thereby contributing novel insights into black hole properties.

gr-qc↗

arXiv2025

FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis

Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own, often for humor, provocation, or controversy. Detecting and analyzing parody can be challenging and is often reliant on context, yet it plays a crucial role in understanding cultural values, promoting subcultures, and enhancing self-expression. However, the study of parody is hindered by limited available data and deficient diversity in current datasets. To bridge this gap, we built seven parody datasets from both English and Chinese corpora, with 14,755 annotated users and 21,210 annotated comments in total. To provide sufficient context information, we also collect replies and construct user-interaction graphs to provide richer contextual information, which is lacking in existing datasets. With these datasets, we test traditional methods and Large Language Models (LLMs) on three key tasks: (1) parody detection, (2) comment sentiment analysis with parody, and (3) user sentiment analysis with parody. Our extensive experiments reveal that parody-related tasks still remain challenging for all models, and contextual information plays a critical role. Interestingly, we find that, in certain scenarios, traditional sentence embedding methods combined with simple classifiers can outperform advanced LLMs, i.e. DeepSeek-R1 and GPT-o3, highlighting parody as a significant challenge for LLMs.

cs.CL↗

arXiv2025

A Deep Learning Framework with Geographic Information Adaptive Loss for Remote Sensing Images based UAV Self-Positioning

With the expanding application scope of unmanned aerial vehicles (UAVs), the demand for stable UAV control has significantly increased. However, in complex environments, GPS signals are prone to interference, resulting in ineffective UAV positioning. Therefore, self-positioning of UAVs in GPS-denied environments has become a critical objective. Some methods obtain geolocation information in GPS-denied environments by matching ground objects in the UAV viewpoint with remote sensing images. However, most of these methods only provide coarse-level positioning, which satisfies cross-view geo-localization but cannot support precise UAV positioning tasks. Consequently, this paper focuses on a newer and more challenging task: precise UAV self-positioning based on remote sensing images. This approach not only considers the features of ground objects but also accounts for the spatial distribution of objects in the images. To address this challenge, we present a deep learning framework with geographic information adaptive loss, which achieves precise localization by aligning UAV images with corresponding satellite imagery in fine detail through the integration of geographic information from multiple perspectives. To validate the effectiveness of the proposed method, we conducted a series of experiments. The results demonstrate the method's efficacy in enabling UAVs to achieve precise self-positioning using remote sensing imagery.

cs.CV↗

arXiv2025

A practical Bayesian method for gravitational-wave ringdown analysis with multiple modes

Gravitational-wave (GW) ringdown signals from black holes (BHs) encode crucial information about the gravitational dynamics in the strong-field regime, which offers unique insights into BH properties. In the future, the improving sensitivity of GW detectors is to enable the extraction of multiple quasi-normal modes (QNMs) from ringdown signals. However, incorporating multiple modes drastically enlarges the parameter space, posing computational challenges to data analysis. Inspired by the $F$-statistic method in the continuous GW searches, we develope an algorithm, dubbed as FIREFLY, for accelerating the ringdown signal analysis. FIREFLY analytically marginalizes the amplitude and phase parameters of QNMs to reduce the computational cost and speed up the full-parameter inference from hours to minutes, while achieving consistent posterior and evidence. The acceleration becomes more significant when more QNMs are considered. Rigorously based on the principle of Bayesian inference and importance sampling, our method is statistically interpretable, flexible in prior choice, and compatible with various advanced sampling techniques, providing a new perspective for accelerating future GW data analysis.

gr-qc↗

arXiv2025

FAST-LIVO2 on Resource-Constrained Platforms: LiDAR-Inertial-Visual Odometry with Efficient Memory and Computation

This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with sequential updates, improving computation efficiency significantly while maintaining a similar level of robustness. Additionally, a memory-efficient mapping structure combining a locally unified visual-LiDAR map and a long-term visual map achieves a good trade-off between performance and memory usage. Extensive experiments on x86 and ARM platforms demonstrate the system's robustness and efficiency. On the Hilti dataset, our system achieves a 33% reduction in per-frame runtime and 47% lower memory usage compared to FAST-LIVO2, with only a 3 cm increase in RMSE. Despite this slight accuracy trade-off, our system remains competitive, outperforming state-of-the-art (SOTA) LIO methods such as FAST-LIO2 and most existing LIVO systems. These results validate the system's capability for scalable deployment on resource-constrained edge computing platforms.

cs.RO↗

arXiv2025

Procedural Fairness and Its Relationship with Distributive Fairness in Machine Learning

Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, there has been limited exploration of procedural fairness. This paper proposes a novel method to achieve procedural fairness during the model training phase. The effectiveness of the proposed method is validated through experiments conducted on one synthetic and six real-world datasets. Additionally, this work studies the relationship between procedural fairness and distributive fairness in ML models. On one hand, the impact of dataset bias and the procedural fairness of ML model on its distributive fairness is examined. The results highlight a significant influence of both dataset bias and procedural fairness on distributive fairness. On the other hand, the distinctions between optimizing procedural and distributive fairness metrics are analyzed. Experimental results demonstrate that optimizing procedural fairness metrics mitigates biases introduced or amplified by the decision-making process, thereby ensuring fairness in the decision-making process itself, as well as improving distributive fairness. In contrast, optimizing distributive fairness metrics encourages the ML model's decision-making process to favor disadvantaged groups, counterbalancing the inherent preferences for advantaged groups present in the dataset and ultimately achieving distributive fairness.

cs.LG↗